Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 8-GEMMASCOPE-TRANSCODER-16K
    4. 1026
    Prev
    Next
    INDEX
    Explanations

    sentences describing events in the past with specific ages or dates

    oai_token-act-pair · gemini-2.0-flash

    Clyde

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_8/width_16k/average_l0_52
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (;;)
    -0.50
    ội
    -0.49
    тябрь
    -0.48
     applied
    -0.43
    Vanjske
    -0.43
    твер
    -0.42
    BRO
    -0.41
    obra
    -0.41
    oula
    -0.41
    quem
    -0.41
    POSITIVE LOGITS
    NameInMap
    0.90
    //
    0.75
    queryInterface
    0.72
     AspNetCore
    0.71
    aarrggbb
    0.69
     otomatig
    0.69
    ConstraintMaker
    0.68
    Kids
    0.68
    setVerticalGroup
    0.65
    protoimpl
    0.63
    Activations Density 2.729%

    No Known Activations